start-render

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does well: it discloses that rendering happens out-of-process in the background, that it operates on the on-disk saved project, that unsaved changes cause a refusal unless saveProject is set, and that it returns an async jobId. It stops short of error behavior, concurrency limits (can two renders overlap?), or how cancellation interacts with cancel-render.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with zero filler; the core action and the responsiveness benefit are front-loaded, followed by the project-file constraint and then the return value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async, no-output-schema tool the description covers what an agent needs to call it and what comes back (jobId for render-status). Minor gaps remain: prerequisites such as aerender availability, what happens if a render is already running, and failure reporting.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented in the schema, giving a baseline of 3. The description reinforces saveProject's consequence ('renders the SAVED project file'), but adds no detail about itemIndices ordering, out-of-range behavior, or partial selection.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('Render the render queue') plus the underlying mechanism (aerender as a separate AE process), and implicitly separates it from the single-frame sibling render-frame. It also states the unit of work (the whole queue / default every item) and the return value (jobId).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The rationale ('so After Effects and the bridge stay responsive') implies this is the non-blocking way to render a queue, but there is no explicit when-to-use versus render-frame, run-script, or the fact that you must poll render-status afterwards. The only concrete directive is behavioral (renders the SAVED file), not a usage rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.